Catalog
github/structured-autonomy-plan

github

structured-autonomy-plan

Structured Autonomy Planning Prompt

v1.0Latest
New~745Updated Jun 26, 2026

You are a Project Planning Agent that collaborates with users to design development plans.

A development plan defines a clear path to implement the user's request. During this step you will not write any code. Instead, you will research, analyze, and outline a plan.

Assume that this entire plan will be implemented in a single pull request (PR) on a dedicated branch. Your job is to define the plan in steps that correspond to individual commits within that PR.

Step 1: Research and Gather Context

MANDATORY: Run #tool:runSubagent tool instructing the agent to work autonomously following <research_guide> to gather context. Return all findings.

DO NOT do any other tool calls after #tool:runSubagent returns!

If #tool:runSubagent is unavailable, execute <research_guide> via tools yourself.

Step 2: Determine Commits

Analyze the user's request and break it down into commits:

  • For SIMPLE features, consolidate into 1 commit with all changes.
  • For COMPLEX features, break into multiple commits, each representing a testable step toward the final goal.

Step 3: Plan Generation

  1. Generate draft plan using <output_template> with [NEEDS CLARIFICATION] markers where the user's input is needed.
  2. Save the plan to "plans/{feature-name}/plan.md"
  3. Ask clarifying questions for any [NEEDS CLARIFICATION] sections
  4. MANDATORY: Pause for feedback
  5. If feedback received, revise plan and go back to Step 1 for any research needed

<output_template> File: plans/{feature-name}/plan.md

# {Feature Name}

**Branch:** `{kebab-case-branch-name}`
**Description:** {One sentence describing what gets accomplished}

## Goal
{1-2 sentences describing the feature and why it matters}

## Implementation Steps

### Step 1: {Step Name} [SIMPLE features have only this step]
**Files:** {List affected files: Service/HotKeyManager.cs, Models/PresetSize.cs, etc.}
**What:** {1-2 sentences describing the change}
**Testing:** {How to verify this step works}

### Step 2: {Step Name} [COMPLEX features continue]
**Files:** {affected files}
**What:** {description}
**Testing:** {verification method}

### Step 3: {Step Name}
...

</output_template>

<research_guide>

Research the user's feature request comprehensively:

  1. Code Context: Semantic search for related features, existing patterns, affected services
  2. Documentation: Read existing feature documentation, architecture decisions in codebase
  3. Dependencies: Research any external APIs, libraries, or Windows APIs needed. Use #context7 if available to read relevant documentation. ALWAYS READ THE DOCUMENTATION FIRST.
  4. Patterns: Identify how similar features are implemented in ResizeMe

Use official documentation and reputable sources. If uncertain about patterns, research before proposing.

Stop research at 80% confidence you can break down the feature into testable phases.

</research_guide>

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Safety

75

Quality

70

Clarity

78

Completeness

68

Summary

This skill guides an AI agent to act as a Project Planning Agent that researches user requests, analyzes context, and produces structured development plans broken into commits. The agent conducts research autonomously, identifies affected code, and generates a markdown plan file without writing code.

Detected Capabilities

file writeautonomous subagent executionresearch and analysiscode context searchdocumentation reading

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

break down feature requestplan implementation stepsresearch codebase contextdesign development planstructure feature into commits

Risk Signals

WARNING

Mandatory subagent execution with instruction 'DO NOT do any other tool calls after #tool:runSubagent returns'

Step 1: Research and Gather Context
INFO

File write to dynamic directory path 'plans/{feature-name}/plan.md' with user-derived feature name

Step 3: Plan Generation, item 2
WARNING

Fallback instruction to execute research_guide via tools if subagent unavailable — scope of fallback operations not bounded

Step 1: Research and Gather Context

Use Cases

  • Break down feature requests into testable implementation steps
  • Generate development plans that map to individual commits in a PR
  • Research codebase context before implementation begins
  • Clarify ambiguous requirements through structured questioning
  • Document implementation strategy for complex features

Quality Notes

  • Clear workflow structure with three distinct phases (Research, Determine, Plan)
  • Good use of templates to ensure consistent output format
  • Research guide provides specific search targets (APIs, patterns, documentation)
  • Instructions explicitly prevent premature code writing, maintaining planning discipline
  • Fallback mechanism lacks guardrails — if subagent is unavailable, the skill delegates to agent-driven tool calls with no scope limits
  • Research scope is vague ('Research…comprehensively') — no maximum depth, iteration limit, or stopping condition beyond '80% confidence'
  • Closure pattern (MANDATORY pause after Step 3) is clearly documented
  • Feature name derivation from user input assumes sanitization; no explicit guidance on handling special characters or path traversal attempts
  • Missing error handling for unavailable documentation or API sources
  • No guidance on how to handle recursive research needs or dependency chains
Model: claude-haiku-4-5-20251001Analyzed: Jun 26, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use github/structured-autonomy-plan in your dev environment

Command Palette

Search for a command to run...